© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43827
    Prev
    Next
    INDEX
    Explanations

    asterisks and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    of
    1.34
    it
    1.17
    ب
    1.13
     sombre
    1.02
    ת
    1.02
    其他
    0.97
    ка
    0.97
    تها
    0.96
    剰
    0.94
    น
    0.93
    POSITIVE LOGITS
     with
    1.00
     from
    0.96
    <0x80>
    0.95
    সহ
    0.93
    р
    0.89
     on
    0.89
    IN
    0.87
    OS
    0.86
    OC
    0.85
    0
    0.85
    Activations Density 0.000%

    No Known Activations